Accurate Force Field for Molybdenum by Machine Learning Large Materials Data

By Chi Chen, Z. Deng, Richard Tran, Hanmei Tang, Iek Heng Chu, Shyue Ping Ong. 2017

129 citations recorded by the source corpus.

In this work, we present a highly accurate spectral neighbor analysis potential (SNAP) model for molybdenum (Mo) developed through the rigorous application of machine learning techniques on large materials data sets. Despite Mo's importance as a structural metal, existing force fields for Mo based on the embedded atom and modified embedded atom methods still do not provide satisfactory accuracy on many properties. We will show that by fitting to the energies, forces and stress tensors of a large density functional theory (DFT)-computed dataset on a diverse set of Mo structures, a Mo SNAP model can be developed that achieves close to DFT accuracy in the prediction of a broad range of properties, including energies, forces, stresses, elastic constants, melting point, phonon spectra, surface energies, grain boundary energies, etc. We will outline a systematic model development process, which includes a rigorous approach to structural selection based on principal component analysis, as well as a differential evolution algorithm for optimizing the hyperparameters in the model fitting so that both the model error and the property prediction error can be simultaneously lowered. We expect that this newly developed Mo SNAP model will find broad applications in large-scale, long-time scale simulations.

Subfields: Materials Chemistry, Surfaces, Coatings and Films

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Surfaces, Coatings and Films

Citations in the corpus

Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals (2018, methodology): “19,20 28 The key input to any ML model is a description of the material, which must satisfy the necessary rotational, translational and permutational invariances as well as uniqueness.”
Machine-Learning Interatomic Potentials for Materials Science (2021, methodology): “The most common choices are the Gaussian process regression [80, 95, 97–101] (underlying the GAP potentials), the kernel ridge regression [29, 102, 103], the SNAP model [75, 96, 104], the MTP potentials [90], and the artificial neural network (NN) regression [21, 40, 68, 69, 105–113].”
Machine Learning a General-Purpose Interatomic Potential for Silicon (2018, methodology): “Using the original spherical bispectrum as a representation, potentials were made with linear regression for tantalum [71] and molybdenum [72], with quadratic regression for tantalum [73], and with a nonlinear kernel for bulk Li2B12H12 [74].”
A Performance and Cost Assessment of Machine Learning Interatomic Potentials. (2019, background): “ electron density contributed by its neighboring atoms. The \host" electron density of embedding atom i can be expressed as a linear function of the bispectrum components as follows: i = a B i; (17) and the embedding energy can be expressed as a Taylor expansion based on a reference structure w”